{"id":"W1604614341","doi":"10.1109/tifs.2015.2434600","title":"A Strategy of Clustering Modification Directions in Spatial Image Steganography","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":231,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; Binghamton University; Sun Yat-sen University; National Natural Science Foundation of China; McGill University","keywords":"Embedding; Steganalysis; Pixel; Computer science; Steganography; Distortion (music); Cluster analysis; Distortion function; Image (mathematics); Artificial intelligence; Cover (algebra); Pattern recognition (psychology); Exploit; Data mining; Algorithm; Computer security; Telecommunications","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002130936,0.0001064919,0.0001268354,0.0004395184,0.00008914089,0.00008273545,0.0001414607,0.00007052782,7.803944e-7],"category_scores_gemma":[0.000003387855,0.0001054998,0.00005415186,0.0004802821,0.00007484095,0.00192046,0.000003994943,0.0001595829,0.000001131355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002470597,"about_ca_system_score_gemma":0.00002953778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001944031,"about_ca_topic_score_gemma":0.0002729942,"domain_scores_codex":[0.9992039,0.00003505676,0.0003411943,0.0001151249,0.0001754807,0.0001292962],"domain_scores_gemma":[0.9994106,0.00002511058,0.0001204836,0.0002206652,0.0001544766,0.00006870947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002680636,0.0003881879,0.0003745279,0.0002525525,0.00005270139,0.000003487134,0.02833359,0.0307879,0.0004824228,0.04474301,0.0001412465,0.8941723],"study_design_scores_gemma":[0.00217813,0.0007055716,0.002579815,0.000146818,0.00002464807,0.00003721974,0.001117189,0.8232715,0.04198814,0.1256567,0.001627685,0.0006665967],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02402592,0.00001124333,0.9744648,0.00006236214,0.0001831557,0.0001790289,0.00002200211,0.0001220552,0.0009294243],"genre_scores_gemma":[0.9846272,0.0000699911,0.01523148,0.00003019293,0.000005502515,0.00002522157,0.000005526182,0.000003035007,0.00000179429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9606013,"threshold_uncertainty_score":0.4302156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01978568003926702,"score_gpt":0.2530372185795924,"score_spread":0.2332515385403254,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}